-
公开(公告)号：US09916679B2
公开(公告)日：2018-03-13
申请号：US15154417
申请日：2016-05-13
申请人： Google Inc.
发明人： John Flynn , Keith Snavely , Ivan Neulander , James Philbin
CPC分类号： G06T15/20 , G06K9/00664 , G06K9/4628 , G06K9/4652 , G06K9/6272 , G06N99/005 , G06T15/205
摘要： A system and method of deep learning using deep networks to predict new views from existing images may generate and improve models and representations from large-scale data. This system and method of deep learning may employ a deep architecture performing new view synthesis directly from pixels, trained from large numbers of posed image sets. A system employing this type of deep network may produce pixels of an unseen view based on pixels of neighboring views, lending itself to applications in graphics generation.
-
公开(公告)号：US20160328866A1
公开(公告)日：2016-11-10
申请号：US14704959
申请日：2015-05-05
申请人： Google Inc.
发明人： Ivan Neulander
CPC分类号： G06T11/20 , B44F11/02 , G06K9/00 , G06K9/00221 , G06T11/001 , G06T11/203 , G06T13/80 , G06T2200/24 , G06T2207/10004 , G06T2207/30201
摘要： A system for animated painterly picture generation comprises a processor and a memory storing instructions that, when executed, cause the system to: determine a first set of brush strokes, each brush strokes being based on a two-dimensional vector; generate a first frame from the first set of brush strokes; perturb the first set of brush strokes to create additional sets of brush strokes; and generate additional frames from the additional sets of brush strokes, wherein the first frame, and the additional frames form a sequence of frames that are time-coherent.
摘要翻译： 一种用于动画画面生成的系统包括处理器和存储指令的存储器，所述指令在执行时使所述系统：确定第一组画笔笔画，每个画笔笔画基于二维向量; 从第一组画笔笔画生成第一帧; 扰乱第一组画笔笔画以创建额外的画笔笔触; 并且从附加的画笔笔画集合生成附加帧，其中第一帧和附加帧形成时间相干的帧序列。
-
公开(公告)号：US09691431B2
公开(公告)日：2017-06-27
申请号：US14885285
申请日：2015-10-16
申请人： Google Inc.
发明人： Shengyang Dai , Timothy Sepkoski St. Clair , Koji Ashida , Jingyu Cui , Jay Steele , Qi Gu , Erik Murphy-Chutorian , Ivan Neulander , Flavio Lerda , Eric Charles Henry , Shinko Yuanhsien Cheng , Aravind Krishnaswamy , David Cohen , Pardis Beikzadeh
CPC分类号： G11B27/036 , G11B27/034 , G11B27/10 , G11B27/105 , G11B27/28 , G11B27/34 , H04N5/2628 , H04N5/7605
摘要： A method includes grouping media items associated with a user into segments based on a timestamp associated with each media item and a total number of media items. The method also includes selecting target media from the media items for each of the segments based on media attributes associated with the media item. The method also includes generating a video that includes the target media for each of the segments by generating a first animation that illustrates a first transition from a first item from the target media to a second item from the target media with movement of the first item from an onscreen location to an offscreen location, wherein the first item is adjacent to the second item in the first animation and determining whether the target media includes one or more additional items. The method also includes adding a song to the video.
-
4.发明申请公开(公告)号：US20160335795A1
公开(公告)日：2016-11-17
申请号：US15154417
申请日：2016-05-13
申请人： Google Inc.
发明人： John Flynn , Keith Snavely , Ivan Neulander , James Philbin
IPC分类号： G06T15/20
CPC分类号： G06T15/20 , G06K9/00664 , G06K9/4628 , G06K9/4652 , G06K9/6272 , G06N99/005 , G06T15/205
摘要： A system and method of deep learning using deep networks to predict new views from existing images may generate and improve models and representations from large-scale data. This system and method of deep learning may employ a deep architecture performing new view synthesis directly from pixels, trained from large numbers of posed image sets. A system employing this type of deep network may produce pixels of an unseen view based on pixels of neighboring views, lending itself to applications in graphics generation.
摘要翻译： 使用深层网络深入学习从现有图像预测新视图的系统和方法可能会生成并改进大型数据的模型和表示。 这种深度学习的系统和方法可以采用深入的架构，直接从像素中执行新的视图合成，从大量呈现的图像集训练。 采用这种类型的深度网络的系统可以基于相邻视图的像素产生不可见视图的像素，从而将其自身应用于图形生成中。
-
公开(公告)号：US10242711B2
公开(公告)日：2019-03-26
申请号：US15633011
申请日：2017-06-26
申请人： Google Inc.
发明人： Shengyang Dai , Timothy Sepkoski St. Clair , Koji Ashida , Jingyu Cui , Jay Steele , Qi Gu , Erik Murphy-Chutorian , Ivan Neulander , Flavio Lerda , Eric Charles Henry , Shinko Yuanhsien Cheng , Aravind Krishnaswamy , David Cohen , Pardis Beikzadeh
IPC分类号： H04N9/80 , H04N5/93 , G11B27/036 , G11B27/034 , G11B27/10 , H04N5/76 , G11B27/34 , G11B27/28 , H04N5/262
摘要： A method includes grouping media items associated with a user into segments based on a timestamp associated with each media item and a total number of media items. The method also includes selecting target media from the media items for each of the segments based on media attributes associated with the media item. The method also includes generating a video that includes the target media for each of the segments by generating a first animation that illustrates a first transition from a first item from the target media to a second item from the target media with movement of the first item from an onscreen location to an offscreen location, wherein the first item is adjacent to the second item in the first animation and determining whether the target media includes one or more additional items. The method also includes adding a song to the video.
-
公开(公告)号：US09842416B2
公开(公告)日：2017-12-12
申请号：US14704959
申请日：2015-05-05
申请人： Google Inc.
发明人： Ivan Neulander
CPC分类号： G06T11/20 , B44F11/02 , G06K9/00 , G06K9/00221 , G06T11/001 , G06T11/203 , G06T13/80 , G06T2200/24 , G06T2207/10004 , G06T2207/30201
摘要： A system for animated painterly picture generation comprises a processor and a memory storing instructions that, when executed, cause the system to: determine a first set of brush strokes, each brush stroke being based on a two-dimensional vector; generate a first frame from the first set of brush strokes; perturb the first set of brush strokes to create additional sets of brush strokes; and generate additional frames from the additional sets of brush strokes, wherein the first frame and the additional frames form a sequence of frames that are time-coherent.
-
公开(公告)号：US09767582B2
公开(公告)日：2017-09-19
申请号：US14704957
申请日：2015-05-05
申请人： Google Inc.
发明人： Ivan Neulander
CPC分类号： G06T11/20 , G06K9/00221 , G06T11/001
摘要： A system for generating painterly pictures comprises a processor and a memory storing instructions that, when executed, cause the system to receive an input image; add a base layer of brush strokes based on a sampling of underlying pixel values in the input image, the base layer comprising coarse large brush strokes that are well-distributed in a uniform pattern; add a uniform layer of brush strokes iteratively based on a sampling of underlying pixel values in the input image and directionally based on a gradient of the input image; and add a detail layer of brush strokes based on a determined saliency map. The disclosure also includes similar methods and computer program products for generating painterly pictures.
-
公开(公告)号：US20160328865A1
公开(公告)日：2016-11-10
申请号：US14704957
申请日：2015-05-05
申请人： Google Inc.
发明人： Ivan Neulander
CPC分类号： G06T11/20 , G06K9/00221 , G06T11/001
摘要： A system for generating painterly pictures comprises a processor and a memory storing instructions that, when executed, cause the system to receive an input image; add a base layer of brush strokes based on a sampling of underlying pixel values in the input image, the base layer comprising coarse large brush strokes that are well-distributed in a uniform pattern; add a uniform layer of brush strokes iteratively based on a sampling of underlying pixel values in the input image and directionally based on a gradient of the input image; and add a detail layer of brush strokes based on a determined saliency map. The disclosure also includes similar methods and computer program products for generating painterly pictures.
摘要翻译： 一种用于产生画家画面的系统包括处理器和存储指令的存储器，所述指令在执行时使系统接收输入图像; 基于输入图像中的底层像素值的采样来添加画笔笔触的基本层，该基本层包括以均匀图案分布良好的粗略大笔画笔划; 基于输入图像中的底层像素值的取样并基于输入图像的梯度方向地迭代地迭代地添加均匀的画笔笔划层; 并根据确定的显着性图添加画笔笔触的细节层。 本公开还包括用于产生画家图片的类似方法和计算机程序产品。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.014 秒)
